This poster is published under an
open license. Please read the
disclaimer for further details.
Type:
Educational Exhibit
Keywords:
Osteoporosis, Chronic obstructive airways disease, Computer Applications-General, CAD, CT-Quantitative, Thorax, Lung, Bones
Authors:
S. Röhrich1, H. Prosch1, W. H. Sommer2, K. Thierfelder3, G. Langs1; 1Vienna/AT, 2München/DE, 3Munich/DE
DOI:
10.1594/ecr2017/C-2000
Background
Radiomics is an emerging field that harvests comprehensive multi-variate information from images to predict disease course and / or prognosis,
and is predominantly used in oncology (1-3).
For example,
comorbidities, such as Chronic Obstructive Pulmonary Disease (COPD) or congestive heart disease,
have a major impact on survival in lung cancer (4,
5).
Therefore,
a diagnostic approach that includes only tumor-specific factors falls short of a comprehensive characterization of all the individual traits of a patient,
which is necessary for personalized-medicine (6).
With the emergence of powerful machine-learning approaches,
routine imaging data and patient records are becoming accessible for the identification of predictive markers.
The exponentially growing amount of available medical data,
with approximately 110 million computed tomography (CT) examinations per year in the EU (7),
constitutes a data source that would both benefit from and contribute to the development of efficient computational imaging analysis methods.